3 papers indexed here
We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.
Not the right person? Other researchers publish under this name.
Geometry-Optimized Few-Step Reinforcement Learning is introduced, built on a selection principle: at a fixed conditioning state and timestep pair, choose the admissible policy that minimizes the conditional KL divergence induced by any given nonzero velocity-output update.
ReSOT is proposed, a unified framework that Re-balances Semantic ID learning via Optimal Transport for GR and provides a principled tokenization scheme that preserves relational structure while assigning codes in a collision-aware and semantics-consistent manner.
Generative recommendation (GR) reformulates sequential recommendation as an autoregressive generation problem, where items are represented as discrete semantic IDs. However, learning effective item tokenization is critical yet remains challenging. Most existing methods optimize tokenization in a point-wise or heuristic...
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
